Add Phase 2 normalization diagnostics

internal/core/diagnostics/run_dir.go

@@ -0,0 +1,145 @@
+package diagnostics
+
+import (
+	"encoding/json"
+	"fmt"
+	"os"
+	"path/filepath"
+	"time"
+
+	"gitea.maximumdirect.net/eric/audita/internal/core/normalization"
+	"gitea.maximumdirect.net/eric/audita/internal/core/reporting"
+	"gitea.maximumdirect.net/eric/audita/internal/core/schema"
+)
+
+// RunDirectory represents a per-run diagnostics directory
+type RunDirectory struct {
+	path        string
+	retention   string
+	createdAt   time.Time
+	sourceSaved bool
+}
+
+// NewRunDirectory creates a new run directory under the configured work dir
+func NewRunDirectory(workDir, retention string) (*RunDirectory, error) {
+	if workDir == "" {
+		workDir = ".audita-runs"
+	}
+
+	// Create work directory if it doesn't exist
+	if err := os.MkdirAll(workDir, 0o755); err != nil {
+		return nil, fmt.Errorf("failed to create work directory %q: %w", workDir, err)
+	}
+
+	// Create unique run directory with timestamp
+	timestamp := time.Now().UTC().Format("2006-01-02T15-04-05Z")
+	runID := fmt.Sprintf("run-%s", timestamp)
+	runPath := filepath.Join(workDir, runID)
+
+	if err := os.Mkdir(runPath, 0o755); err != nil {
+		return nil, fmt.Errorf("failed to create run directory %q: %w", runPath, err)
+	}
+
+	return &RunDirectory{
+		path:      runPath,
+		retention: retention,
+		createdAt: time.Now().UTC(),
+	}, nil
+}
+
+// Path returns the run directory path
+func (r *RunDirectory) Path() string {
+	return r.path
+}
+
+// WriteSourceTranscript writes the source transcript artifact
+func (r *RunDirectory) WriteSourceTranscript(transcript *schema.SourceTranscript, raw []byte) error {
+	// Write raw source for reference
+	sourcePath := filepath.Join(r.path, "source-transcript.json")
+	if err := os.WriteFile(sourcePath, raw, 0o644); err != nil {
+		return fmt.Errorf("failed to write source transcript: %w", err)
+	}
+
+	// Write parsed source for debugging
+	parsedPath := filepath.Join(r.path, "source-transcript-parsed.json")
+	parsedBytes, err := json.MarshalIndent(transcript, "", "  ")
+	if err != nil {
+		return fmt.Errorf("failed to marshal parsed source transcript: %w", err)
+	}
+	parsedBytes = append(parsedBytes, '\n')
+	if err := os.WriteFile(parsedPath, parsedBytes, 0o644); err != nil {
+		return fmt.Errorf("failed to write parsed source transcript: %w", err)
+	}
+
+	r.sourceSaved = true
+	return nil
+}
+
+// WriteNormalizedTranscript writes the normalized transcript artifact
+func (r *RunDirectory) WriteNormalizedTranscript(transcript *schema.Transcript) error {
+	normalizedPath := filepath.Join(r.path, "normalized-transcript.json")
+	bytes, err := schema.TranscriptToJSON(transcript)
+	if err != nil {
+		return fmt.Errorf("failed to serialize normalized transcript: %w", err)
+	}
+	if err := os.WriteFile(normalizedPath, bytes, 0o644); err != nil {
+		return fmt.Errorf("failed to write normalized transcript: %w", err)
+	}
+	return nil
+}
+
+// WriteNormalizationSummary writes the normalization summary artifact
+func (r *RunDirectory) WriteNormalizationSummary(summary *normalization.NormalizationSummary) error {
+	summaryPath := filepath.Join(r.path, "normalization-summary.json")
+	bytes, err := json.MarshalIndent(summary, "", "  ")
+	if err != nil {
+		return fmt.Errorf("failed to marshal normalization summary: %w", err)
+	}
+	bytes = append(bytes, '\n')
+	if err := os.WriteFile(summaryPath, bytes, 0o644); err != nil {
+		return fmt.Errorf("failed to write normalization summary: %w", err)
+	}
+	return nil
+}
+
+// WriteReport writes the authoritative report artifact
+func (r *RunDirectory) WriteReport(report reporting.ProcessReport) error {
+	reportPath := filepath.Join(r.path, "report.json")
+	bytes, err := json.MarshalIndent(report, "", "  ")
+	if err != nil {
+		return fmt.Errorf("failed to marshal report: %w", err)
+	}
+	bytes = append(bytes, '\n')
+	if err := os.WriteFile(reportPath, bytes, 0o644); err != nil {
+		return fmt.Errorf("failed to write report: %w", err)
+	}
+	return nil
+}
+
+// WriteErrorLog writes an error log on failure
+func (r *RunDirectory) WriteErrorLog(errorMessage string) error {
+	errorPath := filepath.Join(r.path, "error.log")
+	return os.WriteFile(errorPath, []byte(errorMessage+"\n"), 0o644)
+}
+
+// ApplyRetention applies the retention policy
+// TODO: In later phases, implement full retention logic including:
+// - auto mode should keep runs with skipped corrections
+// - Add proper cleanup of old runs
+// - Consider disk space limits
+func (r *RunDirectory) ApplyRetention() error {
+	// For Phase 2, implement minimal retention:
+	// - always: keep everything (do nothing)
+	// - never: remove successful runs
+	// - auto: remove successful runs (same as never for now)
+	// - failed runs are always kept (handled by caller)
+
+	if r.retention == "never" || r.retention == "auto" {
+		// Remove successful runs
+		if r.sourceSaved { // Simple heuristic: if we saved source, it was successful
+			return os.RemoveAll(r.path)
+		}
+	}
+	// always: keep everything, or failed runs: keep everything
+	return nil
+}